Studying a softmax-attention model, we show that the learned query converges to the latent signal subspace spanned by the informative direction.
problem Understanding the theoretical principles of attention mechanisms in large-scale token collections.
method Deriving a population objective and analyzing the limiting ordinary differential equation of the learning dynamics.
result The learned query asymptotically recovers the latent signal up to the intrinsic sign ambiguity.
This paper analyzes the interpolation error of nonlinear Attention compared to linear regression.
problem Understanding the interpolation error of nonlinear Attention in high-dimensional settings.
method Derives explicit expressions for mean-squared interpolation error using signal-plus-noise model and random matrix theory.
result Nonlinear Attention generally incurs a larger interpolation error than linear regression, but this gap can be reversed with structured signals.
Study reveals how attention helps in signal recovery from sequence models using random matrix theory.
problem Signal recovery from sequence models with attention mechanisms.
method Analysis of sample covariance matrices constructed from pooled sequence representations with attention weights.
result Optimal attention weights maximize signal-to-noise ratio and improve signal recovery.
This paper explains GNNs using graph signal denoising.
problem Understanding how GNNs work for node representation learning.
method Spectral graph convolutional networks and graph attention networks are analyzed from the perspective of graph signal denoising.
result GNNs implicitly solve graph signal denoising problems.
Attention mechanism combines bottom-up and top-down signals in neural networks.
problem Combining robust perception with bottom-up and top-down signals.
method Attention mechanism over modulated recurrent neural networks.
result Bidirectional information flow leads to improved performance in various tasks.
Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components, unimportant sensor modalities, etc.). Besides, it is difficult to interpret the r…
Attention mechanism learns to focus on sparse tokens efficiently.
problem Detecting weak, rare, and sparsely located features in long sequences.
method Theoretical analysis and training of a single-layer attention classifier in a sparse-token classification model.
result A single-layer attention classifier can achieve vanishing test error with logarithmic signal strength growth, unlike linear classifiers requiring linear growth.
AIMM-X monitors markets for suspicious behavior using transparent scoring.
problem Detecting market manipulation from benign mechanisms.
method Combines microstructure signals and public attention signals for anomaly detection.
result Transparent scoring allows tracing and understanding flagged windows.
Attention models can overfit without harming test performance.
problem Understanding benign overfitting in single-head attention models.
method Analyzing conditions for benign overfitting in a single-head softmax attention model.
result A single-head attention model can overfit without harming test performance under certain conditions.
Novel method segments heart sound signals using LSTMs with attention.
problem Heart sound segmentation for diagnostic applications.
method Bidirectional LSTMs with attention mechanisms.
result State-of-the-art performance on multiple benchmarks.
A-MMSE uses attention to learn efficient OFDM channel estimation.
problem Accurate OFDM channel estimation requires second-order statistics, which are hard to obtain in practice.
method A-MMSE is a model-based DNN framework that learns linear MMSE filters via Attention Transformer, reducing inference complexity.
result A-MMSE outperforms other methods in normalized MSE across various SNR conditions.
LARA forecasts financial asset trends by refining noisy labels and extracting profitable samples.
problem Low signal-to-noise ratio and stochastic nature of financial data lead to poor predictions.
method LARA combines LA-Attention and RA-Labeling to refine and extract profitable samples.
result LARA significantly outperforms existing methods on Qlib platform.
HANET combines LSTM and attention mechanisms for better financial forecasting.
problem Lack of distinct macroeconomic regimes in financial datasets.
method Hierarchical Cross-Attention mechanism integrating long-run macro contexts with high-frequency market dynamics.
result HANET outperforms neural forecasters, especially during turbulent periods.
Paper proposes integrating wavelet transform, channel attention, and LSTM for better stock price prediction.
problem Inherently difficult stock price prediction due to low signal-to-noise ratio.
method Wavelet transform convolution, channel attention, and LSTM integration.
result Robust performance in post-pandemic market conditions.
Deep vanilla transformers trained without shortcuts achieve similar performance to standard models.
problem Training deep vanilla transformers without shortcuts and normalizations.
method Parameter initializations, bias matrices, and location-dependent rescaling.
result Deep vanilla transformers can train at similar speeds and performance to standard models.
Simple attention model outperforms complex sEMG classifiers.
problem Improving myoelectric control for robotic prosthetics.
method Attention-based model for sEMG signal classification.
result Simple model achieves benchmark results on multiple datasets.
Develops a framework for identifying mispriced assets through attention factors for statistical arbitrage.
problem Identifying mispriced assets in statistical arbitrage trading.
method Uses conditional latent factors learned from firm characteristic embeddings to identify time-series signals and form a trading strategy.
result Achieves an out-of-sample Sharpe ratio above 4 on the largest U.S. equities over a 24-year period.
Mind wandering (MW) is a ubiquitous phenomenon which reflects a shift in attention from task-related to task-unrelated thoughts. There is a need for intelligent interfaces that can reorient attention when MW is detected due to its detrimental effects on performance and productivity. In this paper, we propose a deep lea…
This study analyzes why attention layers in neural networks can cause signal loss and proposes a solution.
problem Pathological behavior of attention layers in neural networks, leading to signal loss.
method Spectral analysis using Random Matrix Theory to identify and mitigate rank collapse in width.
result A novel solution to mitigate rank collapse in width by removing outlier eigenvalues.
The Hype Index measures media attention to equities using NLP.
problem Quantifying media attention to equities for volatility analysis.
method Constructs News Count-Based and Capitalization Adjusted Hype Indices using NLP.
result The Hype Index family provides valuable tools for stock volatility analysis.
Improving the performance of click-through rate (CTR) prediction remains one of the core tasks in online advertising systems. With the rise of deep learning, CTR prediction models with deep networks remarkably enhance model capacities. In deep CTR models, exploiting users' historical data is essential for learning user…
MPTE uses Transformer attention to estimate mixed-frequency factor models.
problem Estimating factor models in panel datasets with mixed frequencies and nonlinear signals.
method Mixed-Panels-Transformer Encoder (MPTE) with attention mechanisms.
result MPTE achieves competitive performance in nonlinear forecasting environments.
MultiImport infers node importance from multiple KG signals.
problem Inferring node importance in a knowledge graph from multiple input signals.
method End-to-end latent variable model using attentive graph neural networks.
result MultiImport consistently outperforms existing methods, achieving up to 23.7% higher NDCG@100.
Transformers can solve complex filtering problems for non-Gaussian signals.
problem Non-linear and non-Markovian filtering problems for conditionally Gaussian signals.
method Continuous-time transformer models called filterformers.
result Filterformers can approximate the conditional law of non-Markovian and conditionally Gaussian signal processes.
New theory explains signal propagation in normalization-free transformers.
problem Understanding signal propagation in normalization-free transformers.
method Deriving recurrence relations for activation statistics and APJNs across layers.
result Transformers with elementwise tanh-like nonlinearities exhibit subcritical signal propagation.
Music highlights are valuable contents for music services. Most methods focused on low-level signal features. We propose a method for extracting highlights using high-level features from convolutional recurrent attention networks (CRAN). CRAN utilizes convolution and recurrent layers for sequential learning with an att…
In this paper we demonstrate end-to-end continuous speech recognition (CSR) using electroencephalography (EEG) signals with no speech signal as input. An attention model based automatic speech recognition (ASR) and connectionist temporal classification (CTC) based ASR systems were implemented for performing recognition…
Investor selects portfolios based on news attention in a hidden Markov model.
problem Mean-variance portfolio selection in a dynamic attention context.
method Closed-loop equilibrium strategies via extended HJB equation and Markov chain approximation.
result Equilibrium strategies found through iterative algorithm and numerical examples.
The relation between performance and stress is described by the Yerkes-Dodson Law but varies significantly between individuals. This paper describes a method for determining the individual optimal performance as a function of physiological signals. The method is based on attention and reasoning tests of increasing comp…
Self attention mechanisms have become a key building block in many state-of-the-art language understanding models. In this paper, we show that the self attention operator can be formulated in terms of 1x1 convolution operations. Following this observation, we propose several novel operators: First, we introduce a 2D ve…
Unified theory explains two failure modes of deep transformers and provides initialisation guidelines.
problem Two failure modes (rank collapse and entropy collapse) of self-attention layers in deep transformers.
method Analytical theory of signal propagation through deep transformers, using the Random Energy Model analogy.
result Simple algorithm to compute trainability diagrams for correct initialisation hyper-parameters.
Neural nets predict user attention from mouse movements.
problem Predicting user attention from mouse cursor movements.
method Investigated different mouse movement representations and trained neural networks.
result Neural networks outperform handcrafted features for predicting user attention.
NeoMLP improves neural fields by adding self-attention for better downstream tasks.
problem Complexity and lack of conditioning mechanisms in neural fields.
method Transformed MLP into NeoMLP with self-attention and weight-sharing.
result NeoMLP outperforms state-of-the-art methods in downstream tasks.
TabPFN model shows strong robustness to noisy data.
problem TabPFN tackles robustness to noisy and imperfect tabular data.
method Empirical robustness analysis of TabPFN's attention mechanisms under various perturbations.
result TabPFN maintains high predictive performance and coherent internal behavior under noisy and imperfect data.
Attention learns PCA on Gaussian data, proving its connection to principal component analysis.
problem Principal component analysis on Gaussian data.
method Analysis of attention mechanisms through PCA, covering finite and infinite prompt regimes.
result Attention aligns with principal eigenvectors of covariance matrices, converging to optimal solutions in the infinite-prompt limit.
Language models fail to process hallucinated responses, and this study diagnoses the failure.
problem Language models fail to process hallucinated responses, leading to over-concentration or diffuse attention.
method The study uses forced scoring of benchmark-labeled responses to compute attention shapes and analyze the symmetric component of the degree-normalized attention operator.
result The study proves that every transpose-invariant spectral diagnostic of the attention operator is orientation-blind and bounds the sensitivity of any Lipschitz diagnostic by the asymmetry coefficient \(G\).
Effective theory for Transformer initialization improves model performance.
problem Improving performance of Transformers at initialization.
method Effective-theory analysis of signal propagation in wide and deep Transformers.
result Particular width scalings of initialization and training hyperparameters.
Improved speech enhancement with MNTFA using time-frequency attention.
problem Speech enhancement with limited model size and memory.
method Designing MNTFA with self-attention modules for long sequences and joint training.
result MNTFA achieves better performance with fewer parameters than DPCRN.
UniPhyNet improves cognitive load classification accuracy using EEG, ECG, and EDA signals.
problem Classifying cognitive load using multimodal physiological data.
method Unified network architecture integrating multiscale parallel convolutional blocks, ResNet-type blocks, and channel block attention module. Uses bidirectional gated recurrent unit for temporal dependencies.
result Improves raw signal classification accuracy from 70% to 80% (binary) and 62% to 74% (ternary) on CL-Drive dataset.
Interprets how intrinsic motivation shapes behavior in RL agents.
problem Understanding how intrinsic motivation influences behavior in reinforcement learning agents.
method Analyzed five RL agents in procedurally generated environments using various interpretability techniques.
result Curiosity-driven agents exhibit broader and more dynamic attention than extrinsically motivated agents.
This research integrates attention into XAI frameworks for better model explanations.
problem Improving the interpretability of transformer models.
method Developed two novel explanation methods: Shapley value decomposition and token-level directional derivatives.
result Attention weights can be meaningfully incorporated into XAI frameworks, enhancing transformer explainability.
The p-Laplacian Transformer improves transformer models by assigning higher attention weights to tokens in close proximity.
problem The self-attention mechanism in transformers does not effectively distinguish attention weights between tokens in close and non-close proximity.
method Proposes a novel class of transformers, p-Laplacian Transformers, that use p-Laplacian regularization to assign higher attention weights to tokens in close proximity. result Empirically demonstrates that p-Laplacian Transformers outperform baseline transformers on various benchmark datasets.
Self-attention model improves HAR from wearable sensors.
problem Capturing spatio-temporal context from sensor data.
method Proposes a self-attention based neural network model.
result Significant performance improvement over state-of-the-art models.
Proposes Textual Echo Cancellation to improve speech recognition.
problem Improving speech recognition performance and user experience for smart devices.
method A novel sequence-to-sequence model with multi-source attention that processes both the microphone mixture signal and source text of TTS playback.
result Demonstrates enhanced speech recognition performance and reduced latency.
Speech enhancement improved by adapting to unknown speakers without auxiliary signals.
problem Improving speech enhancement accuracy for unknown speakers.
method Adopting multi-task learning for speech enhancement and speaker identification, using multi-head self-attention.
result Achieved state-of-the-art performance and improved subjective quality.
Transformer models show distinct spectral fingerprints under voice changes.
problem Detecting architectural biases in transformer models.
method Spectral analysis of attention-induced token graphs.
result Clear architectural signatures in model fingerprints correlate with language-specific behavior.
Unlike images or videos data which can be easily labeled by human being, sensor data annotation is a time-consuming process. However, traditional methods of human activity recognition require a large amount of such strictly labeled data for training classifiers. In this paper, we present an attention-based convolutiona…
Physiological signals that provide the objective repression of human affective states are attracted increasing attention in the emotion recognition field. However, the single signal is difficult to obtain completely and accurately description for emotion. Multiple physiological signals fusing models, building the unifo…